When Your AI Agent Restarts Mid-Task: Building Durable Workflows in Spring Boot

The first agentic feature I shipped looked great in demos. The LLM picked a tool, called it, looked at the result, decided what to do next. Three tool calls, clean output, happy stakeholders. Then we put it in front of real users. Within a week we had three incidents. A user retried a request because it felt slow, and we created two support tickets instead of one. A deploy restarted the pod mid-workflow, and the agent simply forgot what it was doing — the user got a half-finished response and...